Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Storage01:23

Storage

84
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
84
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

744
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
744
Interference and Decay01:16

Interference and Decay

135
Forgetting is a complex cognitive phenomenon influenced by several factors, among which interference and decay are particularly prominent. These processes explain why individuals often struggle to retrieve specific information from memory, leading to lapses in recall that can be observed in everyday situations.
Interference occurs when competing memories hinder the retrieval of particular information. It can be classified into two types: proactive and retroactive interference. Proactive...
135
Neural Circuits01:25

Neural Circuits

1.2K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.2K
Dissociative Disorders01:27

Dissociative Disorders

65
Dissociative disorders represent complex psychological conditions characterized by disruptions in consciousness, memory, identity, or perception. These disruptions cause individuals to experience a disconnection from their thoughts, emotions, and memories. The phenomenon is not merely an occasional lapse in attention but a profound alteration in mental functioning that can severely impact daily life.
Dissociative Fugue
A hallmark feature of dissociative disorders is the dissociative fugue...
65
Implicit Memories01:24

Implicit Memories

127
Implicit memories, also known as non-declarative memories, are long-term memories that function outside of conscious awareness. These memories influence behavior and skills without explicit knowledge. This type of memory is evident in tasks like playing tennis, snowboarding, and texting. Implicit memory has three subsystems: procedural memory, conditioning, and priming. This type of memory is essential in various activities, from everyday tasks to specialized skills.
One key aspect of implicit...
127

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The Information Dynamics of Generative Diffusion.

Entropy (Basel, Switzerland)·2026
Same author

The Statistical Thermodynamics of Generative Diffusion Models: Phase Transitions, Symmetry Breaking, and Critical Instability.

Entropy (Basel, Switzerland)·2025
Same author

Rethinking the hippocampal cognitive map as a meta-learning computational module.

Trends in cognitive sciences·2023
Same author

Brain2Pix: Fully convolutional naturalistic video frame reconstruction from brain activity.

Frontiers in neuroscience·2022
Same author

Towards Naturalistic Speech Decoding from Intracranial Brain Data.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2022
Same author

Optimizing an existing prediction model for quality of life one-year post-intensive care unit: An exploratory analysis.

Acta anaesthesiologica Scandinavica·2022
Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026
Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026
Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026
Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026
Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026
Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026
See all related articles
  1. Home
  3. In Search Of Dispersed Memories: Generative Diffusion Models Are Associative Memory Networks.
  1. Home
  3. In Search Of Dispersed Memories: Generative Diffusion Models Are Associative Memory Networks.

Related Experiment Video

Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
09:38

Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Published on: November 14, 2017

14.9K

In Search of Dispersed Memories: Generative Diffusion Models Are Associative Memory Networks.

Luca Ambrogioni1

  • 1Donders Institute for Brain, Cognition, and Behaviour, Radboud University, 6525 XZ Nijmegen, The Netherlands.

Entropy (Basel, Switzerland)
|May 24, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

Generative diffusion models are equivalent to modern Hopfield networks for associative memory. This discovery unifies creative generation and memory recall within a single framework for understanding long-term memory formation.

Keywords:
associative memory networksgenerative diffusion modelshopfield networks

More Related Videos

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans
07:17

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans

Published on: June 23, 2022

2.4K
A Lateralized Odor Learning Model in Neonatal Rats for Dissecting Neural Circuitry Underpinning Memory Formation
10:42

A Lateralized Odor Learning Model in Neonatal Rats for Dissecting Neural Circuitry Underpinning Memory Formation

Published on: August 18, 2014

8.9K

Related Experiment Videos

Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
09:38

Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Published on: November 14, 2017

14.9K
Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans
07:17

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans

Published on: June 23, 2022

2.4K
A Lateralized Odor Learning Model in Neonatal Rats for Dissecting Neural Circuitry Underpinning Memory Formation
10:42

A Lateralized Odor Learning Model in Neonatal Rats for Dissecting Neural Circuitry Underpinning Memory Formation

Published on: August 18, 2014

8.9K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Understanding long-term memory mechanisms is a key challenge in neuroscience and AI.
  • Artificial associative memory networks model biological memory aspects.
  • Generative diffusion models excel at various machine learning tasks.

Purpose of the Study:

  • To interpret generative diffusion models as energy-based models.
  • To establish an equivalence between diffusion models and modern Hopfield networks.
  • To develop a unified framework for long-term memory, creative generation, and recall.

Main Methods:

  • Interpreting generative diffusion models as energy-based models.
  • Training diffusion models on discrete patterns.
  • Analyzing the energy function of trained diffusion models.
  • Comparing the energy function to that of modern Hopfield networks.

    • Main Results:

    • Generative diffusion models can be viewed as energy-based models.
    • When trained on discrete patterns, their energy function is identical to modern Hopfield networks.
    • Supervised training of diffusion models corresponds to synaptic learning in Hopfield networks.

    Conclusions:

    • A strong theoretical link exists between generative diffusion models and modern Hopfield networks.
    • This connection provides a new perspective on synaptic learning and associative dynamics.
    • A unified framework for long-term memory, encompassing generation and recall, is proposed.